From b1d9fc41aab11f9520b2e0d57ae872e2ec5d6f32 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 19 Apr 2017 23:01:17 +0200 Subject: bpf: add napi_id read access to __sk_buff Add napi_id access to __sk_buff for socket filter program types, tc program types and other bpf_convert_ctx_access() users. Having access to skb->napi_id is useful for per RX queue listener siloing, f.e. in combination with SO_ATTACH_REUSEPORT_EBPF and when busy polling is used, meaning SO_REUSEPORT enabled listeners can then select the corresponding socket at SYN time already [1]. The skb is marked via skb_mark_napi_id() early in the receive path (e.g., napi_gro_receive()). Currently, sockets can only use SO_INCOMING_NAPI_ID from 6d4339028b35 ("net: Introduce SO_INCOMING_NAPI_ID") as a socket option to look up the NAPI ID associated with the queue for steering, which requires a prior sk_mark_napi_id() after the socket was looked up. Semantics for the __sk_buff napi_id access are similar, meaning if skb->napi_id is < MIN_NAPI_ID (e.g. outgoing packets using sender_cpu), then an invalid napi_id of 0 is returned to the program, otherwise a valid non-zero napi_id. [1] http://netdevconf.org/2.1/slides/apr6/dumazet-BUSY-POLLING-Netdev-2.1.pdf Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- net/core/filter.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'net') diff --git a/net/core/filter.c b/net/core/filter.c index 085925834727..9a37860a80fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -53,6 +53,7 @@ #include #include #include +#include /** * sk_filter_trim_cap - run a packet through a socket filter @@ -3201,6 +3202,19 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct __sk_buff, napi_id): +#if defined(CONFIG_NET_RX_BUSY_POLL) + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, napi_id) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct sk_buff, napi_id)); + *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); + *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); +#else + *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; } -- cgit v1.2.3